TY  - CONF
AU  - Mayet, Frank
AU  - Hellert, Thorsten
AU  - Sulc, Antonin
AU  - Tennant, Christopher
TI  - Toward Particle Accelerator Machine State Embeddings as a Modality for Large Language Models
M1  - PUBDB-2025-03902
SP  - 965-970
PY  - 2025
AB  - Understanding and diagnosing the state of a particle accelerator requires navigating high-dimensional control system data, often involving hundreds of interdependent parameters. We propose a novel multimodal embedding framework that jointly learns representations of machine states from both numerical control system readouts and natural language descriptions. This enables the translation of complex machine conditions into human-readable summaries while maintaining fidelity to the underlying physical system. The obtained embeddings are subsequently adapted to an open-weights large language model via cross-attention conditioning. We demonstrate a first implementation trained on European XFEL machine state data. This work covers the embedding model architecture, training methodology, and presents initial examples demonstrating the model's capabilities in action. Due to the general concept of machine state, the model can be easily adapted to other facilities and control system environments.
T2  - 20th International Conference on Accelerator and Large Experimental Physics Control Systems, ICALEPCS
CY  - 20 Sep 2025 - 26 Sep 2025, Chicago (USA)
Y2  - 20 Sep 2025 - 26 Sep 2025
M2  - Chicago, USA
LB  - PUB:(DE-HGF)8
DO  - DOI:10.18429/JACoW-ICALEPCS2025-WEPD082
UR  - https://bib-pubdb1.desy.de/record/637851
ER  -